According to an aspect, there is provided a computing device for performing the following. The computing device obtains, in a code editor, one or more logical lines of code for a program. The computing device predicts, using a first prediction algorithm, one or more most probable next program instructions based on said one or more logical lines of code and displays them to the user. In response to receiving a selection of a program instruction, the computing device inserts a selected program instruction to the code editor. The computing device predicts, using a second prediction algorithm, one or more most probable sets of zero or more parameters based on a selected program instruction and said one or more logical lines of code and displays them to the user. In response to receiving a selection of a set, the computing device inserts a selected set to the code editor.
Legal claims defining the scope of protection, as filed with the USPTO.
3. The computing device according to claim 1, wherein the predicting using one or both of the first prediction algorithm and the second prediction algorithm is based on both contents of said one or more logical lines of code and an order of said one or more logical lines of code.
4. The computing device according to claim 1, wherein the first prediction algorithm is a first trained machine-learning algorithm, a first weighted search tree algorithm or a first fuzzy search based prediction algorithm and the second prediction algorithm is a second trained machine-learning algorithm or a second fuzzy search based prediction algorithm.
5. The computing device according to claim 1, wherein the first prediction algorithm has been generated based on a first data set comprising at least finished code for a first set of programs defining a first plurality of sequences of program instructions and the second prediction algorithm has been generated based on a second data set comprising at least finished code for a second set of programs defining a second plurality of sequences of program instructions and sets of zero or more parameters of the program instructions in the second plurality of sequences, the first data set being a generic data set encompassing multiple use cases and applications and the second data being specific at least to a particular use case or application.
6. The computing device according to claim 5, wherein the first set of programs consists of programs created by a plurality of users and the second set of programs consists only of programs created previously by the user or a pre-defined group of users to which the user belongs.
7. The computing device according to claim 5, wherein the first trained machine-learning algorithm and/or the second trained machine-learning algorithm is based on one or more neural networks or one or more support vector machines, the one or more neural networks comprising one or more recurrent neural networks, one or more convolutional neural networks or a combination thereof.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
April 28, 2021
February 7, 2023
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.